Visible to the public Conditional Generative Adversarial Network on Semi-supervised Learning Task

TitleConditional Generative Adversarial Network on Semi-supervised Learning Task
Publication TypeConference Paper
Year of Publication2019
AuthorsMin, Congwen, Li, Yi, Fang, Li, Chen, Ping
Conference Name2019 IEEE 5th International Conference on Computer and Communications (ICCC)
Keywordsabundant unlabeled data, conditional, conditional GAN model, conditional generative adversarial network, Data models, deep neural networks, Gallium nitride, Generative Adversarial Learning, generative adversarial network, generative adversarial networks, Generators, image classification, Mathematical model, Metrics, MNIST dataset, neural nets, pubcrawl, resilience, Resiliency, Scalability, semi-supervised, Semisupervised learning, semisupervised learning method, supervised learning, Tensile stress

Semi-supervised learning has recently gained increasingly attention because it can combine abundant unlabeled data with carefully labeled data to train deep neural networks. However, common semi-supervised methods deeply rely on the quality of pseudo labels. In this paper, we proposed a new semi-supervised learning method based on Generative Adversarial Network (GAN), by using discriminator to learn the feature of both labeled and unlabeled data, instead of generating pseudo labels that cannot all be correct. Our approach, semi-supervised conditional GAN (SCGAN), builds upon the conditional GAN model, extending it to semi-supervised learning by changing the discriminator's output to a classification output and a real or false output. We evaluate our approach with basic semi-supervised model on MNIST dataset. It shows that our approach achieves the classification accuracy with 84.15%, outperforming the basic semi-supervised model with 72.94%, when labeled data are 1/600 of all data.

Citation Keymin_conditional_2019